Credal Concept Bottleneck Models: Structural Separation of Epistemic and Aleatoric Uncertainty

TL;DR

This paper introduces a novel credal-set approach to separate epistemic and aleatoric uncertainties in predictive models, improving interpretability and reliability in decision-making tasks.

Contribution

It presents a Variational Credal Concept Bottleneck Model with disjoint uncertainty heads, achieving structural separation of uncertainties by design rather than post hoc.

Findings

Reduces correlation between epistemic and aleatoric uncertainty by over tenfold.

Improves alignment of epistemic uncertainty with prediction error.

Enhances the interpretability of uncertainty estimates.

Abstract

Decomposing predictive uncertainty into epistemic (model ignorance) and aleatoric (data ambiguity) components is central to reliable decision making, yet most methods estimate both from the same predictive distribution. Recent empirical and theoretical results show these estimates are typically strongly correlated, so changes in predictive spread simultaneously affect both components and blur their semantics. We propose a credal-set formulation in which uncertainty is represented as a set of predictive distributions, so that epistemic and aleatoric uncertainty correspond to distinct geometric properties: the size of the set versus the noise within its elements. We instantiate this idea in a Variational Credal Concept Bottleneck Model with two disjoint uncertainty heads trained by disjoint objectives and non-overlapping gradient paths, yielding separation by construction rather than post hoc decomposition. Across multi-annotator benchmarks, our approach reduces the correlation between epistemic and aleatoric uncertainty by over an order of magnitude compared to standard methods, while improving the alignment of epistemic uncertainty with prediction error and aleatoric uncertainty with ground-truth ambiguity.